© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83815
    Prev
    Next
    INDEX
    Explanations

    acceleration and speed increase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     premiers
    -0.79
    ziona
    -0.78
    龕
    -0.75
    ibir
    -0.75
     bì
    -0.74
    ónima
    -0.73
    椤
    -0.73
    ᄎ
    -0.72
    elung
    -0.72
    wning
    -0.72
    POSITIVE LOGITS
     speeding
    5.38
     accelerate
    5.13
     speed
    5.09
     уско
    4.94
     accelerated
    4.72
     accelerates
    4.72
     speeds
    4.69
     acceleration
    4.59
    acceler
    4.59
    speed
    4.56
    Activations Density 0.205%

    No Known Activations